Filters








1,009 Hits in 3.7 sec

Robust Multi-view Representation: A Unified Perspective from Multi-view Learning to Domain Adaption

Zhengming Ding, Ming Shao, Yun Fu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
First of all, we formulate a unified learning framework which is able to model most existing multi-view learning and domain adaptation in this line.  ...  adaption.  ...  To solve the above task of imbalanced domain adaptation, they proposed a novel algorithm of domain-constraint transfer coding with constraint P XL 1 X P = I p : A(·) = P X t − P X s Z 2 F + β L Z 2 F ,  ... 
doi:10.24963/ijcai.2018/767 dblp:conf/ijcai/DingSF18 fatcat:s2cwblwxnbgavaeirobiyyfk6e

NI-UDA: Graph Adversarial Domain Adaptation from Non-shared-and-Imbalanced Big Data to Small Imbalanced Applications [article]

Guangyi Xiao, Weiwei Xiang, Huan Liu, Hao Chen, Shun Peng, Jingzhi Guo, Zhiguo Gong
2021 arXiv   pre-print
We propose a new general Graph Adversarial Domain Adaptation (GADA) based on semantic knowledge reasoning of class structure for solving the problem of unsupervised domain adaptation (UDA) from the big  ...  For sparse classes transfer challenge, our HGR layer can aggregate local feature to hierarchy graph nodes by node prediction and enhance domain adversarial aligned feature with hierarchy graph reasoning  ...  2) How to transfer from non-shared imbalanced big data to small imbalanced target domain to achieve reliable domain adaptation.  ... 
arXiv:2108.05061v2 fatcat:ty73gwywhvhgfcpxvpsty2g2vm

Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation [article]

Shuhao Cui, Shuhui Wang, Junbao Zhuo, Liang Li, Qingming Huang, Qi Tian
2021 arXiv   pre-print
Experiments show that our method could boost the adaptation accuracy and robustness under three typical domain adaptation scenarios. The code is available at https://github.com/cuishuhao/BNM.  ...  Due to the domain discrepancy in visual domain adaptation, the performance of source model degrades when bumping into the high data density near decision boundary in target domain.  ...  Unsupervised Domain Adaptation Office-31 [18] and Office-Home [51] are standard benchmarks for unsupervised domain adaptation.  ... 
arXiv:2107.06154v4 fatcat:g72kvvqu4ng2hhqd342jxvr63q

Unsupervised Domain Adaptation in Activity Recognition: a GAN-based Approach

Andrea Rosales Sanabria, Franco Zambonelli, Juan Ye
2021 IEEE Access  
Unsupervised domain adaptation has been successfully applied to tackle this challenge, where the activity knowledge from a well-annotated domain can be transferred to a new, unlabelled domain.  ...  INDEX TERMS Human activity recognition, domain adaptation, ensemble learning, generative adversarial networks, covariate shift, kernel mean matching. • We propose shift-GAN as a general unsupervised domain  ...  These two can be a significant concern for unsupervised domain adaptation.  ... 
doi:10.1109/access.2021.3053704 fatcat:gixi5tc3a5esznflmjwaq7jltq

Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations [article]

Shuhao Cui, Shuhui Wang, Junbao Zhuo, Liang Li, Qingming Huang, Qi Tian
2020 arXiv   pre-print
BNM could boost the learning under typical label insufficient learning scenarios, such as semi-supervised learning, domain adaptation and open domain recognition.  ...  The code is available at https://github.com/cuishuhao/BNM.  ...  Accuracies (%) on Office-Home for ResNet50-based unsupervised domain adaptation methods.  ... 
arXiv:2003.12237v1 fatcat:vojajtsdsvdwvk2umd3se4abgq

Transfer Learning for Speech and Language Processing [article]

Dong Wang, Thomas Fang Zheng
2015 arXiv   pre-print
Transfer learning is closely related to multi-task learning (cross-lingual vs. multilingual), and is traditionally studied in the name of 'model adaptation'.  ...  Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks.  ...  Note that the adaptation can be either supervised or unsupervised.  ... 
arXiv:1511.06066v1 fatcat:vzl3rb5oqvauxk3cva6t5r7jzy

Transfer learning for speech and language processing

Dong Wang, Thomas Fang Zheng
2015 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)  
Transfer learning is closely related to multi-task learning (cross-lingual vs. multilingual), and is traditionally studied in the name of 'model adaptation'.  ...  Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks.  ...  Note that the adaptation can be either supervised or unsupervised.  ... 
doi:10.1109/apsipa.2015.7415532 dblp:conf/apsipa/WangZ15 fatcat:oby5enn52batdhoewb4n3ufo4y

Unsupervised Transfer Learning with Self-Supervised Remedy [article]

Jiabo Huang, Shaogang Gong
2020 arXiv   pre-print
Extensive experiments on four datasets for image clustering tasks reveal the superiority of our model over the state-of-the-art transfer clustering techniques.  ...  Different methods have been studied to address the underlying problem based on different assumptions, e.g. from domain adaptation to zero-shot and few-shot learning.  ...  Unsupervised Transfer Learning. Unsupervised Domain Adaptation (UDA) has been widely studied to transfer knowledge across different data distributions.  ... 
arXiv:2006.04737v1 fatcat:jivttxerg5chhaxo4qdwvtokiq

Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation [chapter]

Zhengming Ding, Sheng Li, Ming Shao, Yun Fu
2018 Lecture Notes in Computer Science  
Unsupervised domain adaptation has caught appealing attentions as it facilitates the unlabeled target learning by borrowing existing well-established source domain knowledge.  ...  Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain to better solve cross-domain distribution divergences.  ...  Conclusion In this paper, we developed a novel Graph Adaptive Knowledge Transfer framework for unsupervised domain adaption.  ... 
doi:10.1007/978-3-030-01216-8_3 fatcat:f5x25sxya5ax7hfoo2uoo5msyq

Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation [article]

Yogesh Balaji, Rama Chellappa, Soheil Feizi
2019 arXiv   pre-print
For mixture distributions, established distance measures such as the Wasserstein distance do not take into account imbalanced mixture proportions.  ...  We demonstrate the effectiveness of the proposed measure in GANs, domain adaptation and adversarial clustering in several benchmark datasets.  ...  UDA for unsupervised tasks For unsupervised tasks on mixture datasets, we use the formulation of Eq (7) to perform domain adaptation.  ... 
arXiv:1902.00415v2 fatcat:4vy5aeme6vh2bhcrpn6p75prya

Cross-Lingual Adaptation for Type Inference [article]

Zhiming Li, Xiaofei Xie, Haoliang Li, Zhengzi Xu, Yi Li, Yang Liu
2021 arXiv   pre-print
Besides, by leveraging data from strongly typed languages, PLATO improves the perplexity of the backbone cross-programming-language model and the performance of downstream cross-lingual transfer for type  ...  In this paper, we propose cross-lingual adaptation of program analysis, which allows us to leverage prior knowledge learned from the labeled dataset of one language and transfer it to the others.  ...  Unsupervised Domain Adaptation As an important case of transfer learning, unsupervised domain adaptation (UDA) has drawn significant attention from the computer vision and natural language processing communities  ... 
arXiv:2107.00157v1 fatcat:elq3ytr7g5glxlypk7gkeapcny

Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective [article]

Jing Zhang and Wanqing Li and Philip Ogunbona and Dong Xu
2019 arXiv   pre-print
The comprehensive problem-oriented review of the advances in transfer learning with respect to the problem has not only revealed the challenges in transfer learning for visual recognition, but also the  ...  This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition.  ...  Partial domain adaptation has a more realistic setting than conventional unsupervised domain adaptation.  ... 
arXiv:1705.04396v3 fatcat:iknfmppi5zca7ljovdlwvdwluu

Deep Generative Adversarial Networks for Image-to-Image Translation: A Review

Aziz Alotaibi
2020 Symmetry  
codes to each domain.  ...  Figure 6 . 6 Style transfer applications with (a) inter-domain attribute transfer and (b) intra-domain attribute transfer [95] .  ...  Appendix A GANILLA GAN for Image-to-Illustration Translation 2020 Hicsonmez et al. [117] XGAN Cross GAN 2020 Royer et al. [43]  ... 
doi:10.3390/sym12101705 fatcat:rqlwjjhrvbc6fhc4mxjjvkwk6i

DIRL: Domain-Invariant Representation Learning for Sim-to-Real Transfer [article]

Ajay Kumar Tanwani
2021 arXiv   pre-print
Experiments on digit domains yield state-of-the-art performance on challenging benchmarks, while sim-to-real transfer of object recognition for vision-based decluttering with a mobile robot improves from  ...  transfer in real scenarios.  ...  The authors would like to thank Matthew Trepte, Daniel Zeng, Kate Sanders, Yi Liu, Lerrel Pinto, Trevor Darrell, and Ken Goldberg for their contributions, feedback and suggestions.  ... 
arXiv:2011.07589v3 fatcat:2pwlfjkeuzernprkg6prqr2r2q

Semi-supervised Optimal Transport with Self-paced Ensemble for Cross-hospital Sepsis Early Detection [article]

Ruiqing Ding, Yu Zhou, Jie Xu, Yan Xie, Qiqiang Liang, He Ren, Yixuan Wang, Yanlin Chen, Leye Wang, Man Huang
2021 arXiv   pre-print
the semi-supervised domain adaptation based on optimal transport theory with self-paced under-sampling to avoid a negative transfer possibly caused by covariate shift and class imbalance.  ...  On the whole, SPSSOT is an end-to-end transfer learning method for Sepsis early detection which can automatically select suitable samples from two domains respectively according to the number of iterations  ...  Unlike common methods for the unsupervised situation, we can further consider the coupling constraints for labeled samples when using OT.  ... 
arXiv:2106.10352v1 fatcat:wwmoxns35jbdzpqaq77rgoh6qe
« Previous Showing results 1 — 15 out of 1,009 results